FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots

TL;DR

FACET introduces a reinforcement learning-based control method for legged robots that enhances force adaptability and compliance, improving robustness during forceful interactions and enabling complex loco-manipulation tasks.

Contribution

The paper presents a novel RL-based impedance reference tracking approach, allowing legged robots to adapt to external forces with improved compliance and robustness, demonstrated in simulation and real-world experiments.

Findings

Achieved 80% reduction in collision impulse in simulation

Demonstrated payload manipulation up to two-thirds of robot weight

Extended method to loco-manipulation and humanoid robots

Abstract

Reinforcement learning (RL) has made significant strides in legged robot control, enabling locomotion across diverse terrains and complex loco-manipulation capabilities. However, the commonly used position or velocity tracking-based objectives are agnostic to forces experienced by the robot, leading to stiff and potentially dangerous behaviors and poor control during forceful interactions. To address this limitation, we present \emph{Force-Adaptive Control via Impedance Reference Tracking} (FACET). Inspired by impedance control, we use RL to train a control policy to imitate a virtual mass-spring-damper system, allowing fine-grained control under external forces by manipulating the virtual spring. In simulation, we demonstrate that our quadruped robot achieves improved robustness to large impulses (up to 200 Ns) and exhibits controllable compliance, achieving an 80% reduction in collision impulse. The policy is deployed to a physical robot to showcase both compliance and the ability to engage with large forces by kinesthetic control and pulling payloads up to 2/3 of its weight. Further extension to a legged loco-manipulator and a humanoid shows the applicability of our method to more complex settings to enable whole-body compliance control. Project Website: https://facet.pages.dev/